Files & data
Read and write files safely; parse JSON, CSV, and common text formats.
Build a File Index by Relative Path Hash Map in Python
Recursively walk a directory and map normalized relative paths to absolute file paths using a defaultdict hash map.
import os
from collections import defaultdict
def build_file_index(root_dir):
index = defaultdict(list)
for dirpath, dirnames, filenames in os.walk(root_dir):
for filename in filenames:
full_path = os.path.join(dirpath, filename)
relative_path = os.path.relpath(full_path, roo…Convert File Data to a Dictionary in Python
This function scans a directory and converts each file's metadata (name, size, extension) into a structured dictionary for easy access.
from pathlib import Path
def convert_files_data(directory: str) -> dict:
data = {}
base = Path(directory)
if not base.exists():
return data
for file in base.iterdir():
if file.is_file():
data[file.name] = {
"size": file.stat().st_size,
"exten…Export List of Dicts to CSV in Python
Write a list of dictionaries (dataframe-like) to a CSV file with headers using the standard library csv module and verify by reading it back.
import csv
def export_to_csv(data, filename):
"""Export a list of dicts to a CSV file."""
if not data:
print("No data to export")
return
# Get column names from the keys of the first dict
fieldnames = list(data[0].keys())
with open(filename, 'w', newline='', encoding='utf…Generate Timesheet Reports from Daily Logs in Python
Aggregate daily log entries by project and produce a formatted timesheet report using Python's standard library.
import json
from pathlib import Path
from collections import defaultdict
def generate_timesheet_report(daily_logs: list[dict]) -> str:
"""
Generate a timesheet report from daily log entries.
Args:
daily_logs: List of dicts with 'date', 'project', 'hours', 'task' keys
Returns:
…How to Group Files by Extension in Python
Group file names by their file extension using a dictionary and pathlib, producing a simple clear mapping for beginners.
from pathlib import Path
def group_data_by_extension(files: list[Path]) -> dict[str, list[str]]:
"""Group file names by their extension."""
grouped: dict[str, list[str]] = {}
for file in files:
ext = file.suffix.lower()
grouped.setdefault(ext, []).append(file.name)
return grouped
if…How to List File Information in a Directory with Python
A helper that walks a directory and returns each file's name, size, and extension as a list of dictionaries.
from pathlib import Path
def get_files_data(directory: str) -> list[dict]:
"""Return basic info about all files in a directory."""
files = []
for path in Path(directory).iterdir():
if path.is_file():
files.append({
"name": path.name,
"size": path.stat()…How to List File Metadata in Python
This code walks a directory and returns a list of JSON-ready dicts with each file's name, size, and modification time.
from pathlib import Path
import json
def format_files_data(directory_path):
"""Return a list of JSON-serializable dicts with file metadata."""
base = Path(directory_path)
if not base.is_dir():
raise ValueError(f"Not a directory: {directory_path}")
files_data = []
for file_path in base.ite…How to Merge Dicts from Two JSON Files Like a Pro
This helper reads two JSON files that contain dicts, merges them with the second file overriding duplicate keys, and saves the result to a new file.
import json
from pathlib import Path
def merge_json_files(file1: str, file2: str, output: str = "merged.json") -> dict:
"""Merge two JSON files containing dicts, with file2 overriding file1."""
data1 = json.loads(Path(file1).read_text())
data2 = json.loads(Path(file2).read_text())
merged = {**data1,…How to Merge Environment-Specific Config JSON in Python
Loads a base JSON config and overlays environment-specific overrides, merging the two dictionaries into one final config.
import json
import pathlib
def load_config(base_path: pathlib.Path, env: str) -> dict:
base_config = json.loads(base_path.read_text())
env_path = base_path.with_name(f"config.{env}.json")
if env_path.exists():
env_config = json.loads(env_path.read_text())
return {**base_config, **env_conf…How to Parse XML Attributes into a Flat Dictionary in Python
Parses XML elements and attributes using ElementTree, building a flat dictionary keyed by element attributes.
import xml.etree.ElementTree as ET
xml_data = """<root>
<book id="1" category="fiction" price="9.99">
<title>The Catcher</title>
</book>
<book id="2" category="nonfiction" price="12.50">
<title>Deep Learning</title>
</book>
</root>"""
def parse_xml_attributes(xml_string):
root = E…How to Read a JSON File into a Dictionary in Python
Load a JSON file into a Python dictionary using the json.load() function with proper file handling and UTF-8 encoding.
import json
from pathlib import Path
def read_json_file(filepath: str) -> dict:
"""Read a JSON file and return its contents as a dictionary."""
path = Path(filepath)
with path.open("r", encoding="utf-8") as f:
data = json.load(f)
return data
if __name__ == "__main__":
# Create a sample JS…How to Read a TSV File in Python with csv.DictReader
Read a tab-separated (TSV) file into dictionaries using the csv module's DictReader with a tab delimiter.
import csv
from pathlib import Path
data_file = Path("data.tsv")
# Sample TSV content (tab-separated)
sample = """name\tage\tcity
Alice\t30\tNew York
Bob\t25\tLos Angeles
Carol\t35\tChicago
"""
data_file.write_text(sample)
with data_file.open("r", newline="", encoding="utf-8") as f:
reader = csv.DictReader(f, d…How to Sort Files by Name and Size in Python
Sort a list of file dictionaries by name then size using Python's sorted() with a lambda key.
from pathlib import Path
def sort_files_data(files):
"""Sort a list of file dictionaries by name, then by size."""
return sorted(files, key=lambda f: (f["name"], f["size"]))
if __name__ == "__main__":
files_data = [
{"name": "report.pdf", "size": 2048},
{"name": "data.csv", "size": 1024},…How to Split Files by Extension in Python
Group files in a folder by their file extension into a dictionary using pathlib.
from pathlib import Path
def split_files_by_extension(folder_path):
folder = Path(folder_path)
files_by_ext = {}
for file_path in folder.iterdir():
if file_path.is_file():
ext = file_path.suffix.lower() or "no_extension"
files_by_ext.setdefault(ext, []).append(file_path.na…How to Sum a CSV Column by Group in Python
This code reads a CSV string and sums a specified column for each unique value of a group key using the csv module and defaultdict.
import csv
from collections import defaultdict
from io import StringIO
def aggregate_csv(csv_data, group_key, sum_column):
totals = defaultdict(float)
reader = csv.DictReader(StringIO(csv_data))
for row in reader:
key = row[group_key]
totals[key] += float(row[sum_column])
return dict(t…How to Validate a JSON File in Python
A beginner-friendly Python helper that reads a JSON file, catches common errors, and returns a status dictionary.
import json
from pathlib import Path
def get_valid_json_data(file_path: str) -> dict:
file = Path(file_path)
if not file.exists():
return {"status": "error", "message": f"File not found: {file_path}"}
try:
data = json.loads(file.read_text())
except json.JSONDecodeError as e:
…How to Write a Dict to a Pretty JSON File with Indent in Python
Serializes a Python dictionary to a readable JSON file using json.dump with indentation and sorted keys, then prints the file contents to stdout.
import json
from pathlib import Path
data = {
"name": "Python",
"version": 3.12,
"features": ["simple", "readable", "powerful"],
"nested": {"creator": "Guido van Rossum", "year": 1991}
}
output_path = Path("output.json")
with output_path.open("w", encoding="utf-8") as f:
json.dump(data, f, inden…Parse Fixed Width Data File by Column Slices in Python
Extract fields from fixed-width text by slicing each line at defined column offsets, with a dictionary describing the boundaries.
from pathlib import Path
def parse_fixed_width(data: str, slices: dict[str, tuple[int, int]]) -> list[dict[str, str]]:
lines = data.strip().splitlines()
records = []
for line in lines:
record = {}
for name, (start, end) in slices.items():
record[name] = line[start:end].strip()…Read SQLite database with sqlite3 module in Python
Connect to a SQLite database and query rows with the standard library sqlite3 module, returning results as dictionaries.
import sqlite3
from pathlib import Path
# Create an in-memory database and a sample table
connection = sqlite3.connect(":memory:")
cursor = connection.cursor()
cursor.execute("""
CREATE TABLE employees (
id INTEGER PRIMARY KEY,
name TEXT NOT NULL,
department TEXT NOT NULL,
salary REAL
)
""")
# Inser…Read a CSV File with csv.DictReader in Python
Read a CSV file as a list of dictionaries, using csv.DictReader to map each row to column names.
import csv
from pathlib import Path
def read_csv_with_dictreader(file_path):
data = []
with open(file_path, mode='r', newline='', encoding='utf-8') as csvfile:
reader = csv.DictReader(csvfile)
for row in reader:
data.append(row)
return data
if __name__ == "__main__":
# Cre…Write CSV file with csv DictWriter in Python
Write a list of dictionaries to a CSV file using Python's csv.DictWriter, including a header row.
import csv
from pathlib import Path
fieldnames = ["name", "city", "age"]
rows = [
{"name": "Alice", "city": "New York", "age": 30},
{"name": "Bob", "city": "Los Angeles", "age": 25},
{"name": "Charlie", "city": "Chicago", "age": 35},
]
path = Path("people.csv")
with path.open("w", newline="") as csvfile:…Browse by section
Each section groups closely related Python snippets.
Files & data — Python code examples
What you will find here
This page collects files & data snippets — short, copy-ready Python you can paste into our free online IDE and run without installing anything. Each sample includes a plain-English explanation and the full source code.
Samples vs tutorials and challenges
Samples are quick reference — one concept per page. For step-by-step teaching, use our Python tutorials. To test yourself, try quizzes or coding challenges. Clean up style with the Python formatter.